Cover Image

Video models are zero-shot learners and reasoners

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wiedemer, Thaddäus, Li, Yuxuan, Vicol, Paul, Gu, Shixiang Shane, Matarese, Nick, Swersky, Kevin, Kim, Been, Jaini, Priyank, Geirhos, Robert
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do generative video models understand physical principles?
by: Motamed, Saman, et al.
Published: (2025)

Intriguing properties of generative classifiers
by: Jaini, Priyank, et al.
Published: (2023)

Directly Fine-Tuning Diffusion Models on Differentiable Rewards
by: Clark, Kevin, et al.
Published: (2023)

We Can't Understand AI Using our Existing Vocabulary
by: Hewitt, John, et al.
Published: (2025)

Neologism Learning for Controllability and Self-Verbalization
by: Hewitt, John, et al.
Published: (2025)

Towards flexible perception with visual memory
by: Geirhos, Robert, et al.
Published: (2024)

Collective Intelligence for 2D Push Manipulations with Mobile Robots
by: Kuroki, So, et al.
Published: (2022)

MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
by: Mayilvahanan, Prasanna, et al.
Published: (2025)

Let people fail! Exploring the influence of explainable virtual and robotic agents in learning-by-doing tasks
by: Matarese, Marco, et al.
Published: (2024)

VL-Explore: Zero-shot Vision-Language Exploration and Target Discovery by Mobile Robots
by: Zhang, Yuxuan, et al.
Published: (2025)

Don't trust your eyes: on the (un)reliability of feature visualizations
by: Geirhos, Robert, et al.
Published: (2023)

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?
by: Mayilvahanan, Prasanna, et al.
Published: (2023)

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
by: Mayilvahanan, Prasanna, et al.
Published: (2025)

Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks
by: Wiedemer, Thaddäus, et al.
Published: (2025)

TC-IDM: Grounding Video Generation for Executable Zero-shot Robot Motion
by: Mi, Weishi, et al.
Published: (2026)

Zero-shot Reconstruction of In-Scene Object Manipulation from Video
by: Lin, Dixuan, et al.
Published: (2025)

Meta-reasoning Using Attention Maps and Its Applications in Cloud Robotics
by: Lendinez, Adrian, et al.
Published: (2025)

Federated reinforcement learning for robot motion planning with zero-shot generalization
by: Yuan, Zhenyuan, et al.
Published: (2024)

How can reasoning capability empower the AI copilot robot in endoscopic surgery
by: Wang, Guankun, et al.
Published: (2026)

ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control
by: Sleiman, Jean Pierre, et al.
Published: (2026)

One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs
by: Wang, Jianren, et al.
Published: (2024)

Provable Compositional Generalization for Object-Centric Learning
by: Wiedemer, Thaddäus, et al.
Published: (2023)

GeoNav: Empowering MLLMs with dual-scale geospatial reasoning for language-goal aerial navigation
by: Xu, Haotian, et al.
Published: (2025)

Obstruction reasoning for robotic grasping
by: Jiao, Runyu, et al.
Published: (2025)

Zero-shot Interactive Perception
by: Sripada, Venkatesh, et al.
Published: (2026)

Recent Advances in Variable‐Stiffness Robotic Systems Enabled by Phase‐Change Materials
by: Sukrit Gaira, et al.
Published: (2025)

Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning
by: He, Pengfei, et al.
Published: (2024)

AED: Adaptable Error Detection for Few-shot Imitation Policy
by: Yeh, Jia-Fong, et al.
Published: (2024)

Navigation under uncertainty: Trajectory prediction and occlusion reasoning with switching dynamical systems
by: Wei, Ran, et al.
Published: (2024)

SurgiPose: Estimating Surgical Tool Kinematics from Monocular Video for Surgical Robot Learning
by: Chen, Juo-Tung, et al.
Published: (2025)

A Clinical Tuning Framework for Continuous Kinematic and Impedance Control of a Powered Knee-Ankle Prosthesis
by: Reznick, Emma, et al.
Published: (2024)

Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation
by: Gu, Songen, et al.
Published: (2026)

Scalable Policy Evaluation with Video World Models
by: Tseng, Wei-Cheng, et al.
Published: (2025)

Show and Grasp: Few-shot Semantic Segmentation for Robot Grasping through Zero-shot Foundation Models
by: Barcellona, Leonardo, et al.
Published: (2024)

VGGSounder: Audio-Visual Evaluations for Foundation Models
by: Zverev, Daniil, et al.
Published: (2025)

Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
by: Chen, Jiahe, et al.
Published: (2026)

Embodied AI with Two Arms: Zero-shot Learning, Safety and Modularity
by: Varley, Jake, et al.
Published: (2024)

MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos
by: Ju, Hyoseok, et al.
Published: (2026)

ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning
by: Mower, Christopher E., et al.
Published: (2024)

Disentangling perception and reasoning for improving data efficiency in learning cloth manipulation without demonstrations
by: Delehelle, Donatien, et al.
Published: (2026)